Name
Abstract | ||
|---|---|---|
A method is proposed in this paper for the detection of suspected central apnea events from nocturnal data measured with pressure sensor arrays. Optimized set of time and frequency measures computed from overlapping segments of 9 s are fed to a support vector machine-based classifier to identify the possible origin of the segments, i.e., not-apneic or apneic episodes. The classifier decision on the sequence of successive segments is then used to detect a complete event. The classifier accuracy for the test data-set and the overall F-score of the system is found to be 94.43% and 74.44%, respectively. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/MeMeA.2019.8802214 | 2019 IEEE International Symposium on Medical Measurements and Applications (MeMeA) |
Keywords | Field | DocType |
central apnea detection,unobtrusive sensors,apnea classification,pressure sensor array | Central apnea,Pattern recognition,Computer science,Support vector machine,Apneic episodes,Apnea,Pressure sensor,Artificial intelligence,Classifier (linguistics),Pressure sensor array | Conference |
ISBN | Citations | PageRank |
978-1-5386-8429-0 | 0 | 0.34 |
References | Authors | |
9 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| H. Azimi | 1 | 6 | 1.90 |
| Martin Bouchard | 2 | 172 | 29.67 |
| Rafik A. Goubran | 3 | 512 | 69.23 |
| Frank Knoefel | 4 | 221 | 32.71 |